Pub Date : 2016-10-01DOI: 10.1109/CISP-BMEI.2016.7852943
D. Cui, Juan Wang, Zhaohui Li, Xiaoli Li
The magnitude squared coherence (MSC) is an important method to calculate the connectivity between neural signals. It provides a better spectral resolution than the Welch's method and is often used in analyzing electroencephalograph (EEG) synchronization activity. The minimum variance distortionless response (MVDR) is a spectral estimation method based on matched filterbank theory. The Cheriet-Belouchrani (CB) kernel is provided for measuring the energy of a signal in time-frequency distribution, which has significant interference mitigation and preserves high resolution measure values. By combining MVDR spectra and CB kernel, a new magnitude squared coherence estimating method is proposed in the paper by smoothing the MVDR with the CB kernel (SMVDR). The simulation results show that SMVDR MSC approach has better performances than the MVDR MSC method.
{"title":"A new coherence estimating method: The magnitude squared coherence of smoothing minimum variance distortionless response","authors":"D. Cui, Juan Wang, Zhaohui Li, Xiaoli Li","doi":"10.1109/CISP-BMEI.2016.7852943","DOIUrl":"https://doi.org/10.1109/CISP-BMEI.2016.7852943","url":null,"abstract":"The magnitude squared coherence (MSC) is an important method to calculate the connectivity between neural signals. It provides a better spectral resolution than the Welch's method and is often used in analyzing electroencephalograph (EEG) synchronization activity. The minimum variance distortionless response (MVDR) is a spectral estimation method based on matched filterbank theory. The Cheriet-Belouchrani (CB) kernel is provided for measuring the energy of a signal in time-frequency distribution, which has significant interference mitigation and preserves high resolution measure values. By combining MVDR spectra and CB kernel, a new magnitude squared coherence estimating method is proposed in the paper by smoothing the MVDR with the CB kernel (SMVDR). The simulation results show that SMVDR MSC approach has better performances than the MVDR MSC method.","PeriodicalId":275095,"journal":{"name":"2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114572962","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-10-01DOI: 10.1109/CISP-BMEI.2016.7853029
Gang Shen, Dan Han
In this paper, we investigate the problem of learning multiple overlapped manifolds from data samples with noise. Learning low dimensional nonlinear manifolds embedded in high dimensional Euclidean space has been an important issue in many data driven pattern analysis applications. The work in this paper extends manifold learning into the complex situations where an unknown number of manifolds may overlap. The approach proposed introduces the notion of flow consisting of multi-agents in a formation exploring a smooth curve on a manifold and thus separating different manifolds. A flow generates an ordered sequence of neighborhoods visited by the agents and can be used to simplify elastic mapping to discover the principal manifold structures. Simulations in various settings demonstrate the effectiveness of the proposed approach.
{"title":"A flow based approach for learning multiple manifolds","authors":"Gang Shen, Dan Han","doi":"10.1109/CISP-BMEI.2016.7853029","DOIUrl":"https://doi.org/10.1109/CISP-BMEI.2016.7853029","url":null,"abstract":"In this paper, we investigate the problem of learning multiple overlapped manifolds from data samples with noise. Learning low dimensional nonlinear manifolds embedded in high dimensional Euclidean space has been an important issue in many data driven pattern analysis applications. The work in this paper extends manifold learning into the complex situations where an unknown number of manifolds may overlap. The approach proposed introduces the notion of flow consisting of multi-agents in a formation exploring a smooth curve on a manifold and thus separating different manifolds. A flow generates an ordered sequence of neighborhoods visited by the agents and can be used to simplify elastic mapping to discover the principal manifold structures. Simulations in various settings demonstrate the effectiveness of the proposed approach.","PeriodicalId":275095,"journal":{"name":"2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116829497","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-10-01DOI: 10.1109/CISP-BMEI.2016.7853024
Bo Chen, Xiu-e Gao, Qingguo Zheng, Jingfeng Wu
The prediction model of existing human body composition based on measured bioelectricity has problems that include redundant influence factors and low prediction accuracy. To address these problems, this paper put forward a human body composition prediction model based on Akaike Information Criterion (AIC) and improved entropy method. First, combining with the AIC information principle, we selected a set of characteristic parameters from human physiological arguments, and constructed the human body composition prediction model; Second, improved entropy method was used to solve the unknown coefficients in predictive model, then worked out prediction model of human body composition; Finally, a comparative analysis experiment of the prediction model and the actual measurement data was designed, and the data were sampled by InBody770 body composition instrument. Experimental results showed that a good correlation existed between the model predictions data and the actual measurements, this study provided a theoretical basis for the model and analysis of human body composition.
基于实测生物电的现有人体成分预测模型存在影响因素过多、预测精度低等问题。针对这些问题，提出了一种基于赤池信息准则(Akaike Information Criterion, AIC)和改进熵值法的人体成分预测模型。首先，结合AIC信息原理，从人体生理参数中选取一组特征参数，构建人体成分预测模型;其次，利用改进的熵值法求解预测模型中的未知系数，建立人体成分预测模型;最后，设计了预测模型与实际测量数据的对比分析实验，并用InBody770体成分仪对数据进行采样。实验结果表明，模型预测数据与实际测量结果具有较好的相关性，为人体成分的建模和分析提供了理论依据。
{"title":"Research on human body composition prediction model based on Akaike Information Criterion and improved entropy method","authors":"Bo Chen, Xiu-e Gao, Qingguo Zheng, Jingfeng Wu","doi":"10.1109/CISP-BMEI.2016.7853024","DOIUrl":"https://doi.org/10.1109/CISP-BMEI.2016.7853024","url":null,"abstract":"The prediction model of existing human body composition based on measured bioelectricity has problems that include redundant influence factors and low prediction accuracy. To address these problems, this paper put forward a human body composition prediction model based on Akaike Information Criterion (AIC) and improved entropy method. First, combining with the AIC information principle, we selected a set of characteristic parameters from human physiological arguments, and constructed the human body composition prediction model; Second, improved entropy method was used to solve the unknown coefficients in predictive model, then worked out prediction model of human body composition; Finally, a comparative analysis experiment of the prediction model and the actual measurement data was designed, and the data were sampled by InBody770 body composition instrument. Experimental results showed that a good correlation existed between the model predictions data and the actual measurements, this study provided a theoretical basis for the model and analysis of human body composition.","PeriodicalId":275095,"journal":{"name":"2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129591854","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-10-01DOI: 10.1109/CISP-BMEI.2016.7852980
Chaofeng Lan, Lei Zhang, Ming Zhu, Jingyu Wang, Ya Zhang
Voltage-gated ion channel is the molecular target for a broad range of toxins. Voltage-gated ion channel toxins are excellent pharmacological tools in toxicology and neuroscience. They have been used as molecular scaffolding agents, drugs, and insecticides. In this study, voltage-gated calcium, potassium and sodium channel toxins are predicted by the increment of diversity (ID) algorithm. Each protein is represented by 400 pseudo amino acid compositions and 9 MEME motif features. The Maximum Relevance Minimum Redundancy (MRMR) is applied for ranking 400 pseudo amino acid compositions. The results of jackknife test indicate that the best predictive results are obtained when using 50 higher ranked pseudo amino acid compositions and 9 MEME motif features. Based on the predictive results, our results suggest the usefulness and potential of ID algorithm for prediction of voltage-gated ion channel toxins using protein sequence derived information.
{"title":"Prediction of voltage-gated ion channel toxins by increment of diversity","authors":"Chaofeng Lan, Lei Zhang, Ming Zhu, Jingyu Wang, Ya Zhang","doi":"10.1109/CISP-BMEI.2016.7852980","DOIUrl":"https://doi.org/10.1109/CISP-BMEI.2016.7852980","url":null,"abstract":"Voltage-gated ion channel is the molecular target for a broad range of toxins. Voltage-gated ion channel toxins are excellent pharmacological tools in toxicology and neuroscience. They have been used as molecular scaffolding agents, drugs, and insecticides. In this study, voltage-gated calcium, potassium and sodium channel toxins are predicted by the increment of diversity (ID) algorithm. Each protein is represented by 400 pseudo amino acid compositions and 9 MEME motif features. The Maximum Relevance Minimum Redundancy (MRMR) is applied for ranking 400 pseudo amino acid compositions. The results of jackknife test indicate that the best predictive results are obtained when using 50 higher ranked pseudo amino acid compositions and 9 MEME motif features. Based on the predictive results, our results suggest the usefulness and potential of ID algorithm for prediction of voltage-gated ion channel toxins using protein sequence derived information.","PeriodicalId":275095,"journal":{"name":"2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128567732","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-10-01DOI: 10.1109/CISP-BMEI.2016.7852817
Y. Wang, Qiong-Hua Wang, Qi Liu, Jun Wang
In this paper, we proposed a novel optical encryption and decryption method of gray image based on the Fourier computer-generated hologram (CGH) and logical modulation. Since the encryption method using the CGH or the logical modulation alone has a shortness of low security, the proposed novel encryption combines the two methods together. In our encryption processing, the hologram, which is gotten by Fourier transform from the original image, is encrypted by logical modulation with the chaotic sequence. Simulation results and analysis show that the security and robustness of the proposed approach has a satisfactory performance.
{"title":"Optical encryption of gray image based on the fourier computer generated hologram and logical modulation","authors":"Y. Wang, Qiong-Hua Wang, Qi Liu, Jun Wang","doi":"10.1109/CISP-BMEI.2016.7852817","DOIUrl":"https://doi.org/10.1109/CISP-BMEI.2016.7852817","url":null,"abstract":"In this paper, we proposed a novel optical encryption and decryption method of gray image based on the Fourier computer-generated hologram (CGH) and logical modulation. Since the encryption method using the CGH or the logical modulation alone has a shortness of low security, the proposed novel encryption combines the two methods together. In our encryption processing, the hologram, which is gotten by Fourier transform from the original image, is encrypted by logical modulation with the chaotic sequence. Simulation results and analysis show that the security and robustness of the proposed approach has a satisfactory performance.","PeriodicalId":275095,"journal":{"name":"2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"135 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124601940","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-10-01DOI: 10.1109/CISP-BMEI.2016.7852919
Jiaqi Wang, Jinjie Yao, G. He, K. Gao, Zhiying Fan
Carrier antenna is the hub of communication between flight and ground station. This kind of antenna is generally curved conformal antennas and its spatial arrangement demands are high. In this paper, the contrast models are built on the plane and curved surface. By theoretical analysis and HFSS simulation, the influence of conformal surface and feeder bending on the performance of microstrip antenna are studied. The results show that the conformal surface will make the antenna performance worse, while the performance of the antenna is optimized with the feeder bending: conformal surface will make the resonance frequency offset, the S-parameter increased, which means more radiation loss and less radiation gain. On the contrary, feeder bending has little effect on the resonant frequency of the antenna, and at the same time, it can not only reduce the S-parameters, also increase the coverage area and gain value of antenna. These results provide a theoretical and simulation basis for the research and application of conformal microstrip antennas in the fields of communication and guidance.
{"title":"Influence of feeder bending and curved surface on microstrip antenna","authors":"Jiaqi Wang, Jinjie Yao, G. He, K. Gao, Zhiying Fan","doi":"10.1109/CISP-BMEI.2016.7852919","DOIUrl":"https://doi.org/10.1109/CISP-BMEI.2016.7852919","url":null,"abstract":"Carrier antenna is the hub of communication between flight and ground station. This kind of antenna is generally curved conformal antennas and its spatial arrangement demands are high. In this paper, the contrast models are built on the plane and curved surface. By theoretical analysis and HFSS simulation, the influence of conformal surface and feeder bending on the performance of microstrip antenna are studied. The results show that the conformal surface will make the antenna performance worse, while the performance of the antenna is optimized with the feeder bending: conformal surface will make the resonance frequency offset, the S-parameter increased, which means more radiation loss and less radiation gain. On the contrary, feeder bending has little effect on the resonant frequency of the antenna, and at the same time, it can not only reduce the S-parameters, also increase the coverage area and gain value of antenna. These results provide a theoretical and simulation basis for the research and application of conformal microstrip antennas in the fields of communication and guidance.","PeriodicalId":275095,"journal":{"name":"2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130355551","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-10-01DOI: 10.1109/CISP-BMEI.2016.7853010
Bruno Mendes Moro Conque, A. Kashiwabara, Fabricio M. Lopes
The development of new genomic sequencing techniques leads to a generation of a huge volume of biological data. In this context, it is important to develop new pattern recognition methods and improve its accuracy in order to support the analysis of these huge volume of data. In particular, a valuable information of the genomic sequences is its nucleotides organization. This work presents an effective feature extraction approach for genomic sequences from complex networks, which is based on mapping the genomic sequences in its representation as complex networks. The nodes of the networks are defined by the combination of nucleotides, dinucleotides or trinucleotides within the sequence by adopting the parameters: Word Size (W S) and Step (ST). The edges are estimated by observing the respective adjacency among the nucleotides in the genomic sequence. These complex network measures are extracted and adopted in order to generate a feature vector for each genomic sequence. For each biological sequence, the entropy, sum of entropy and its maximum value are also adopted. A dataset containing 3 different genomic sequences: coding, intergenic and TSS (Transcriptional Starter Sites) were adopted in order to evaluate the proposed approach. The results were obtained by the following classification methods: Random Forest with 91.2%, followed by J48 with 89.1% and SVM with 84.8% of accuracy without including any source of a priori information, i.e., considering only the genomic sequences. These results indicate the suitability, effectiveness and robustness of the proposed feature extraction approach for the classification of the adopted classes of genomic sequences.
新的基因组测序技术的发展导致了大量生物数据的产生。在此背景下，开发新的模式识别方法并提高其准确性，以支持对这些海量数据的分析是非常重要的。特别是，基因组序列的一个有价值的信息是它的核苷酸组织。本文提出了一种从复杂网络中提取基因组序列特征的有效方法，该方法基于将基因组序列的表示映射为复杂网络。网络的节点由序列内核苷酸、二核苷酸或三核苷酸的组合来定义，采用参数:Word Size (W S)和Step (ST)。通过观察基因组序列中核苷酸之间各自的邻接性来估计边缘。这些复杂的网络度量被提取并用于生成每个基因组序列的特征向量。对于每个生物序列，也采用熵、熵和及其最大值。采用了包含3个不同基因组序列的数据集:编码序列、基因间序列和转录起始位点(TSS)，以评估所提出的方法。在不考虑任何先验信息来源，即只考虑基因组序列的情况下，采用随机森林(Random Forest)的准确率为91.2%，J48的准确率为89.1%，SVM的准确率为84.8%。这些结果表明了所提出的特征提取方法对所采用的基因组序列分类的适用性、有效性和鲁棒性。
{"title":"A feature extraction approach based on complex networks for genomic sequences recognition","authors":"Bruno Mendes Moro Conque, A. Kashiwabara, Fabricio M. Lopes","doi":"10.1109/CISP-BMEI.2016.7853010","DOIUrl":"https://doi.org/10.1109/CISP-BMEI.2016.7853010","url":null,"abstract":"The development of new genomic sequencing techniques leads to a generation of a huge volume of biological data. In this context, it is important to develop new pattern recognition methods and improve its accuracy in order to support the analysis of these huge volume of data. In particular, a valuable information of the genomic sequences is its nucleotides organization. This work presents an effective feature extraction approach for genomic sequences from complex networks, which is based on mapping the genomic sequences in its representation as complex networks. The nodes of the networks are defined by the combination of nucleotides, dinucleotides or trinucleotides within the sequence by adopting the parameters: Word Size (W S) and Step (ST). The edges are estimated by observing the respective adjacency among the nucleotides in the genomic sequence. These complex network measures are extracted and adopted in order to generate a feature vector for each genomic sequence. For each biological sequence, the entropy, sum of entropy and its maximum value are also adopted. A dataset containing 3 different genomic sequences: coding, intergenic and TSS (Transcriptional Starter Sites) were adopted in order to evaluate the proposed approach. The results were obtained by the following classification methods: Random Forest with 91.2%, followed by J48 with 89.1% and SVM with 84.8% of accuracy without including any source of a priori information, i.e., considering only the genomic sequences. These results indicate the suitability, effectiveness and robustness of the proposed feature extraction approach for the classification of the adopted classes of genomic sequences.","PeriodicalId":275095,"journal":{"name":"2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130412745","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-10-01DOI: 10.1109/CISP-BMEI.2016.7853006
Yanning Cai
Nucleosome which is the basic chromatin unit plays an important role in the genome packaging. We found the characteristics of nucleosome positioning among different genes of the human CD4 + cells. It was found that a linear combination of approximately 20 factors explaining the nucleosome positioning of each genome. In these linear combinations, a histone modification and the properties of the 6 DNA sequences are shared. Other factors are different. This study has a high resolution, which greatly simplifies the means to predict and understand the different genomic features in human CD4 + cells, providing a more accurate nucleosome occupancy.
{"title":"Nucleosome positioning determinants for distinct human genomic features","authors":"Yanning Cai","doi":"10.1109/CISP-BMEI.2016.7853006","DOIUrl":"https://doi.org/10.1109/CISP-BMEI.2016.7853006","url":null,"abstract":"Nucleosome which is the basic chromatin unit plays an important role in the genome packaging. We found the characteristics of nucleosome positioning among different genes of the human CD4 + cells. It was found that a linear combination of approximately 20 factors explaining the nucleosome positioning of each genome. In these linear combinations, a histone modification and the properties of the 6 DNA sequences are shared. Other factors are different. This study has a high resolution, which greatly simplifies the means to predict and understand the different genomic features in human CD4 + cells, providing a more accurate nucleosome occupancy.","PeriodicalId":275095,"journal":{"name":"2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126691706","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-10-01DOI: 10.1109/CISP-BMEI.2016.7853011
Yuan Gao, Zhifeng Shi, Yuanyuan Wang, Jinhua Yu, Liang Chen, Yi Guo, Qi Zhang, Y. Mao
Glioma is one of the most common brain tumors with high mortality and its histological grading and typing is important both in therapeutic decision and prognosis evaluation. This paper aims at using the high-throughput image feature analysis method to estimate the histological grade and type of a patient by using Magnetic Resonance Imaging (MRI) instead of histological examination. The proposed method consists of the initial label definition, the region-of-interest delineation, the self-adaptive feature extraction, the feature subset selection, and the multi-class voting classification. Hereinto, a novel feature extraction strategy is designed, which could avoid the MRI scan diversity so as to get the robust feature extraction result and make the proposed framework more stable and effective. This method was validated on a database of 124 patients with the grade II to IV of 78, 25, and 21, and with astrocytoma, oligodendroglioma, oligoastrocytoma of 86, 16, and 22, respectively. We show that by using the leave-one-out cross-validation, the multi-class classification accuracy and macro average could reach 88.71%, 0.8362 respectively for the grade classification, and 70.97%, 0.5692 respectively for the type classification. It can be concluded that the histological grade and subtype information could be estimated from the MRI image analysis.
{"title":"Histological grade and type classification of glioma using Magnetic Resonance Imaging","authors":"Yuan Gao, Zhifeng Shi, Yuanyuan Wang, Jinhua Yu, Liang Chen, Yi Guo, Qi Zhang, Y. Mao","doi":"10.1109/CISP-BMEI.2016.7853011","DOIUrl":"https://doi.org/10.1109/CISP-BMEI.2016.7853011","url":null,"abstract":"Glioma is one of the most common brain tumors with high mortality and its histological grading and typing is important both in therapeutic decision and prognosis evaluation. This paper aims at using the high-throughput image feature analysis method to estimate the histological grade and type of a patient by using Magnetic Resonance Imaging (MRI) instead of histological examination. The proposed method consists of the initial label definition, the region-of-interest delineation, the self-adaptive feature extraction, the feature subset selection, and the multi-class voting classification. Hereinto, a novel feature extraction strategy is designed, which could avoid the MRI scan diversity so as to get the robust feature extraction result and make the proposed framework more stable and effective. This method was validated on a database of 124 patients with the grade II to IV of 78, 25, and 21, and with astrocytoma, oligodendroglioma, oligoastrocytoma of 86, 16, and 22, respectively. We show that by using the leave-one-out cross-validation, the multi-class classification accuracy and macro average could reach 88.71%, 0.8362 respectively for the grade classification, and 70.97%, 0.5692 respectively for the type classification. It can be concluded that the histological grade and subtype information could be estimated from the MRI image analysis.","PeriodicalId":275095,"journal":{"name":"2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130576236","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-10-01DOI: 10.1109/CISP-BMEI.2016.7852859
Shan Liu, Boxin Mao, Jianping Chai
This paper proposed an impact analysis framework of three-dimensional indoor location technology based on RSSI. The impact analysis model is set to compare the location precision under different types of noise. The result illustrate that the designed impact analysis tool achieves the perfect three-dimensional indoor location results combined cost, location accuracy with filter. To reduce the impact of the noise, the secondary location which built various propagation models for different types of environments has been used. And the location accuracy is greatly improved.
{"title":"Impact analysis on three-dimensional indoor location technology","authors":"Shan Liu, Boxin Mao, Jianping Chai","doi":"10.1109/CISP-BMEI.2016.7852859","DOIUrl":"https://doi.org/10.1109/CISP-BMEI.2016.7852859","url":null,"abstract":"This paper proposed an impact analysis framework of three-dimensional indoor location technology based on RSSI. The impact analysis model is set to compare the location precision under different types of noise. The result illustrate that the designed impact analysis tool achieves the perfect three-dimensional indoor location results combined cost, location accuracy with filter. To reduce the impact of the noise, the secondary location which built various propagation models for different types of environments has been used. And the location accuracy is greatly improved.","PeriodicalId":275095,"journal":{"name":"2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114084361","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：